Real-time spatter detection in laser welding with beam oscillation

Martin Wilhelm Haubold; Michael Friedrich Zäh

doi:10.1016/j.procir.2019.02.037

Real-time spatter detection in laser welding with beam oscillation

Martin Wilhelm Haubold, Michael Friedrich Zäh

Chair of Machine Tools and Manufacturing Technology

Technical University of Munich

Research output: Contribution to journal › Conference article › peer-review

11 Scopus citations

Abstract

Spatter formation is a longstanding issue in laser welding. This research addresses this topic and proposes a machine vision algorithm executed on a graphics processing unit to detect spatters in real time. Using this approach, a control system detecting spatter at a rate of 1 kHz and with a resolution of 900 x 900 pixels was implemented. Based on an experimental series, it is shown that the variation of the process parameters has a significant influence on the formation of spatter. It was also possible to quantify the variance of the spatter formation for a given set of process parameters.

Original language	English
Pages (from-to)	159-164
Number of pages	6
Journal	Procedia CIRP
Volume	79
DOIs	https://doi.org/10.1016/j.procir.2019.02.037
State	Published - 2019
Event	12th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2018 - Naples, Italy Duration: 18 Jul 2018 → 20 Jul 2018

Keywords

beam oscillation
graphics processing unit
laser welding
machine vision
spatter formation

Access to Document

10.1016/j.procir.2019.02.037

Cite this

@article{615a9d3ca9ef43568281cadc6250ced7,

title = "Real-time spatter detection in laser welding with beam oscillation",

abstract = "Spatter formation is a longstanding issue in laser welding. This research addresses this topic and proposes a machine vision algorithm executed on a graphics processing unit to detect spatters in real time. Using this approach, a control system detecting spatter at a rate of 1 kHz and with a resolution of 900 x 900 pixels was implemented. Based on an experimental series, it is shown that the variation of the process parameters has a significant influence on the formation of spatter. It was also possible to quantify the variance of the spatter formation for a given set of process parameters.",

keywords = "beam oscillation, graphics processing unit, laser welding, machine vision, spatter formation",

author = "Haubold, {Martin Wilhelm} and Z{\"a}h, {Michael Friedrich}",

note = "Publisher Copyright: {\textcopyright} 2019 The Author(s).; 12th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2018 ; Conference date: 18-07-2018 Through 20-07-2018",

year = "2019",

doi = "10.1016/j.procir.2019.02.037",

language = "English",

volume = "79",

pages = "159--164",

journal = "Procedia CIRP",

issn = "2212-8271",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Real-time spatter detection in laser welding with beam oscillation

AU - Haubold, Martin Wilhelm

AU - Zäh, Michael Friedrich

PY - 2019

Y1 - 2019

N2 - Spatter formation is a longstanding issue in laser welding. This research addresses this topic and proposes a machine vision algorithm executed on a graphics processing unit to detect spatters in real time. Using this approach, a control system detecting spatter at a rate of 1 kHz and with a resolution of 900 x 900 pixels was implemented. Based on an experimental series, it is shown that the variation of the process parameters has a significant influence on the formation of spatter. It was also possible to quantify the variance of the spatter formation for a given set of process parameters.

AB - Spatter formation is a longstanding issue in laser welding. This research addresses this topic and proposes a machine vision algorithm executed on a graphics processing unit to detect spatters in real time. Using this approach, a control system detecting spatter at a rate of 1 kHz and with a resolution of 900 x 900 pixels was implemented. Based on an experimental series, it is shown that the variation of the process parameters has a significant influence on the formation of spatter. It was also possible to quantify the variance of the spatter formation for a given set of process parameters.

KW - beam oscillation

KW - graphics processing unit

KW - laser welding

KW - machine vision

KW - spatter formation

UR - http://www.scopus.com/inward/record.url?scp=85065420273&partnerID=8YFLogxK

U2 - 10.1016/j.procir.2019.02.037

DO - 10.1016/j.procir.2019.02.037

M3 - Conference article

AN - SCOPUS:85065420273

SN - 2212-8271

VL - 79

SP - 159

EP - 164

JO - Procedia CIRP

JF - Procedia CIRP

T2 - 12th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2018

Y2 - 18 July 2018 through 20 July 2018

ER -

Real-time spatter detection in laser welding with beam oscillation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this